© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 260114
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     euc
    0.46
     Studios
    0.45
     EBS
    0.44
     Apt
    0.44
     artery
    0.43
     token
    0.43
    仑
    0.42
    ForResult
    0.42
     Okt
    0.42
    کر
    0.42
    POSITIVE LOGITS
    icke
    0.55
    ɑ
    0.50
    漫画
    0.48
    engah
    0.47
    skyblue
    0.47
    blau
    0.47
    лися
    0.46
    ငယ်
    0.45
     яв
    0.45
    免费
    0.45
    Activations Density 0.000%

    No Known Activations